From 8646b68e5b124f612fd65b51ea40624f65a2f3d6 Mon Sep 17 00:00:00 2001 From: Chris Dyer Date: Mon, 29 Dec 2014 01:59:41 -0500 Subject: finnish abbrevs --- corpus/support/token_patterns | 1 + 1 file changed, 1 insertion(+) (limited to 'corpus/support/token_patterns') diff --git a/corpus/support/token_patterns b/corpus/support/token_patterns index de64fb2a..e51e5e72 100644 --- a/corpus/support/token_patterns +++ b/corpus/support/token_patterns @@ -1,5 +1,6 @@ /^(al|el|ul|e)\-[a-z]+$/ /^((а|А)(ль|ш)|уль)-\p{Cyrillic}+$/ +/^(юл)-\p{Cyrillic}+$/ /^\p{Cyrillic}\.\p{Cyrillic}\.$/ /^(\d|\d\d|\d\d\d)\.$/ -- cgit v1.2.3